junyanz

iGAN

Python2016–2016

junyanz / iGAN

iGAN

Interactive Image Generation via Generative Adversarial Networks

Explore on GitHub Read Hacker News discussions

4Distinct people

5Mentions

0Explicit recommenders

4KGitHub stars

REPOSITORY AT A GLANCE

What to know before exploring

What it is

Interactive Image Generation via Generative Adversarial Networks

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by day5 dated mentions

Observed mentions: 2016-09-21 18:17:11 UTC to 2016-10-02 01:32:03 UTC.

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges

UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
Period	Start (UTC)	End (exclusive, UTC)	Mentions	Submissions	Comments
Sep 21	2016-09-21 00:00:00 UTC	2016-09-22 00:00:00 UTC	1	0	1
Sep 22	2016-09-22 00:00:00 UTC	2016-09-23 00:00:00 UTC	0	0	0
Sep 23	2016-09-23 00:00:00 UTC	2016-09-24 00:00:00 UTC	1	0	1
Sep 24	2016-09-24 00:00:00 UTC	2016-09-25 00:00:00 UTC	1	0	1
Sep 25	2016-09-25 00:00:00 UTC	2016-09-26 00:00:00 UTC	1	1	0
Sep 26	2016-09-26 00:00:00 UTC	2016-09-27 00:00:00 UTC	0	0	0
Sep 27	2016-09-27 00:00:00 UTC	2016-09-28 00:00:00 UTC	0	0	0
Sep 28	2016-09-28 00:00:00 UTC	2016-09-29 00:00:00 UTC	0	0	0
Sep 29	2016-09-29 00:00:00 UTC	2016-09-30 00:00:00 UTC	0	0	0
Sep 30	2016-09-30 00:00:00 UTC	2016-10-01 00:00:00 UTC	0	0	0
Oct 1	2016-10-01 00:00:00 UTC	2016-10-02 00:00:00 UTC	0	0	0
Oct 2	2016-10-02 00:00:00 UTC	2016-10-03 00:00:00 UTC	1	0	1

What Hacker News says

5 sources

xentripetal·Oct 2, 2016

I believe one came out recently, I saw it on GitHub a few days ago. It mainly did landscape and searched for similar images then combined them to form a new one. It also supported image manipulation, eg turning a brown square purse into a green rounded one. I'll see if I can find it and edit the link in. EDIT: https://github.com/junyanz/iGAN Heres a good video showing it off https://www.youtube.com/watch?v=9c4z6YsBGQ0&feature=youtu.be

In The Sketchy Database: Learning to Retrieve Badly Drawn Bunnies

visionp·Sep 25, 2016Submission

iGAN – Deep learning software that generates images with a few brushstrokes

194 points · Open discussion

geforce2060·Sep 24, 2016

NVIDIA shared a similar real-time deep editing demo developed by Adobe and Berkeley (https://www.facebook.com/NVIDIA/videos/10154055823608253/?pn...) several days ago. Adobe's open source prototype: https://github.com/junyanz/iGAN Video: https://people.eecs.berkeley.edu/~junyanz/projects/gvm/

In Neural Photo Editor

visionp·Sep 23, 2016

Very impressive! It reminds me of this image generation and editing work via Generative Adversarial Networks https://www.youtube.com/watch?v=9c4z6YsBGQ0 (https://github.com/junyanz/iGAN) posted before. Seems lots of efforts in this direction.

In Neural Photo Editing with Introspective Adversarial Networks

junyanz·Sep 21, 2016

Thank you guys for the interest. The interactive image generation interface as well as trained models are available at https://github.com/junyanz/iGAN. It is still under active development and let me know if you find bugs or would like to suggest new features.

In Generative Visual Manipulation on the Natural Image Manifold